o Zh[@s>ddlZddlZddlmZddlmZddlmZddlm Z m Z ddl Z ddl Z ddlmZddlmZmZmZmZmZmZmZmZmZmZmZdd lmZmZmZm Z m!Z!m"Z"erddl#Z$ddl%Z$e&e&e$j'j(e&d krye$j)j*Z+ne$j)Z+erdd l,m-Z-e+j.e-j/e+j0e-j0e+j1e-j1e+j2e-j2e+j3e-j3e+j4e-j4iZ5niZ5erddl6Z6e7e8Z9e d e j:d e;d e;e j:e;d fZGdddeZ?e@eAe eBeAe;e@ffZCddZDGdddeZEddZFddZGde;fddZHdd ZId!d"ZJd#d$ZKd%e j:d&eLfd'd(ZMdnd*eBd&e;e<fd+d,ZNde e;e<eeBd?eBd&eReBeBffd@dAZVdBe@eAe e;eRffd&eLfdCdDZWdBe@eAe e;eRffd&eLfdEdFZXdGee@eAe e;eRffd&eLfdHdIZYdGee@eAe e;eRffd&eLfdJdKZZdod%e eAd fdLe e[d&d fdMdNZ\ dode e;eReAd fdLe e[d&e d e;d e;e;d ffdOdPZ]            dpdQe eLdRe e[dSe eLdTe e e[e;e[fdUe e e[e;e[fdVe eLdWe eBdXe eLdYe e@eAeBfdZe eLd[e e@eAeBfd\e d]fd^d_Z^Gd`dadaZ_dbe>dceRe>d4fdGe;e@d&dfdddeZ`dfe;eAdge;eAfdhdiZaedjdkGdldmdmZbdS)qN)Iterable) dataclass)BytesIO)OptionalUnion)version) ExplicitEnum is_jax_tensoris_numpy_array is_tf_tensoris_torch_availableis_torch_tensoris_torchvision_availableis_vision_availableloggingrequires_backendsto_numpy)IMAGENET_DEFAULT_MEANIMAGENET_DEFAULT_STDIMAGENET_STANDARD_MEANIMAGENET_STANDARD_STDOPENAI_CLIP_MEANOPENAI_CLIP_STDz9.1.0)InterpolationModezPIL.Image.Imagez torch.Tensorc@eZdZdZdZdS)ChannelDimensionZchannels_firstZ channels_lastN)__name__ __module__ __qualname__FIRSTLASTr"r"G/var/www/auris/lib/python3.10/site-packages/transformers/image_utils.pyrUrc@r)AnnotationFormatZcoco_detectionZ coco_panopticN)rrrCOCO_DETECTION COCO_PANOPTICr"r"r"r#r%Zr$r%c@seZdZejjZejjZdS)AnnotionFormatN)rrrr%r&valuer'r"r"r"r#r(_s r(cCsto t|tjjSN)r isinstancePILImageimgr"r"r# is_pil_imagegsr0c@s eZdZdZdZdZdZdZdS) ImageTypeZpillowtorchnumpyZ tensorflowZjaxN)rrrr,TORCHNUMPY TENSORFLOWJAXr"r"r"r#r1ks r1cCsXt|rtjSt|rtjSt|rtjSt|rtjSt |r#tj St dt |)NzUnrecognised image type ) r0r1r,rr4r r5r r6r r7 ValueErrortypeimager"r"r#get_image_typessr<cCs(t|pt|pt|pt|pt|Sr*)r0r rr r r.r"r"r#is_valid_images(r=imagescCs|o tdd|DS)Ncs|]}t|VqdSr*)r=.0r;r"r"r# z*is_valid_list_of_images..allr>r"r"r#is_valid_list_of_imagessrGcCs\t|dtrdd|DSt|dtjrtj|ddSt|dtjr,tj|ddSdS)NrcSg|] }|D]}|qqSr"r")rAZsublistitemr"r"r# z$concatenate_list..Zaxis)dim)r+listnpndarrayZ concatenater2Tensorcat)Z input_listr"r"r#concatenate_listsrScCs:t|ttfr|D] }t|sdSq dSt|sdSdS)NFT)r+rNtuple valid_imagesr=)Zimgsr/r"r"r#rUsrUcCst|ttfr t|dSdS)NrF)r+rNrTr=r.r"r"r# is_batcheds rVr;returncCs,|jtjkrdSt|dkot|dkS)zV Checks to see whether the pixel values have already been rescaled to [0, 1]. Frr)dtyperOuint8minmaxr:r"r"r#is_scaled_images r\expected_ndimscCst|r|St|r |gSt|r9|j|dkrt|}|S|j|kr(|g}|Std|dd|d|jdtdt|d)a Ensure that the output is a list of images. If the input is a single image, it is converted to a list of length 1. If the input is a batch of images, it is converted to a list of images. Args: images (`ImageInput`): Image of images to turn into a list of images. expected_ndims (`int`, *optional*, defaults to 3): Expected number of dimensions for a single input image. If the input image has a different number of dimensions, an error is raised. rz%Invalid image shape. Expected either z or z dimensions, but got z dimensions.ztInvalid image type. Expected either PIL.Image.Image, numpy.ndarray, torch.Tensor, tf.Tensor or jax.ndarray, but got .)rVr0r=ndimrNr8r9)r>r^r"r"r#make_list_of_imagess*  racCst|ttfr tdd|Dr tdd|Dr dd|DSt|ttfrHt|rHt|ds8|djdkr:|S|djdkrHd d|DSt|rat|sU|jdkrX|gS|jdkrat|Std |) a| Ensure that the output is a flat list of images. If the input is a single image, it is converted to a list of length 1. If the input is a nested list of images, it is converted to a flat list of images. Args: images (`Union[List[ImageInput], ImageInput]`): The input image. Returns: list: A list of images or a 4d array of images. cs|] }t|ttfVqdSr*r+rNrTrAZimages_ir"r"r#rBz+make_flat_list_of_images..csr?r*rGrdr"r"r#rBrCcSrHr"r"rAZimg_listr/r"r"r#rJrKz,make_flat_list_of_images..rr]cSrHr"r"rgr"r"r#rJrKz*Could not make a flat list of images from r+rNrTrErGr0r`r=r8rFr"r"r#make_flat_list_of_imagess$  rjcCst|ttfrtdd|Drtdd|Dr|St|ttfrDt|rDt|ds3|djdkr6|gS|djdkrDdd|DSt|r_t|sQ|jdkrU|ggS|jdkr_t|gStd ) z Ensure that the output is a nested list of images. Args: images (`Union[List[ImageInput], ImageInput]`): The input image. Returns: list: A list of list of images or a list of 4d array of images. csrbr*rcrdr"r"r#rBrez-make_nested_list_of_images..csr?r*rfrdr"r"r#rBrCrr]rhcSsg|]}t|qSr")rNr@r"r"r#rJsz.make_nested_list_of_images..z]Invalid input type. Must be a single image, a list of images, or a list of batches of images.rirFr"r"r#make_nested_list_of_imagess$   rkcCs@t|s tdt|trt|tjjrt|St |S)NzInvalid image type: ) r=r8r9rr+r,r-rOarrayrr.r"r"r#to_numpy_arrays  rm num_channels.cCs|dur|nd}t|tr|fn|}|jdkrd\}}n|jdkr&d\}}n|jdkr0d\}}ntd|j|j||vrS|j||vrStd |jd tjS|j||vr]tjS|j||vrgtj Std ) a[ Infers the channel dimension format of `image`. Args: image (`np.ndarray`): The image to infer the channel dimension of. num_channels (`int` or `Tuple[int, ...]`, *optional*, defaults to `(1, 3)`): The number of channels of the image. Returns: The channel dimension of the image. Nrr]r])rrh)rprhz(Unsupported number of image dimensions: z4The channel dimension is ambiguous. Got image shape z. Assuming channels are the first dimension. Use the [input_data_format](https://huggingface.co/docs/transformers/main/internal/image_processing_utils#transformers.image_transforms.rescale.input_data_format) parameter to assign the channel dimension.z(Unable to infer channel dimension format) r+intr`r8shapeloggerwarningrr r!)r;rnZ first_dimZlast_dimr"r"r#infer_channel_dimension_format&s&       rvinput_data_formatcCsF|durt|}|tjkr|jdS|tjkr|jdStd|)a Returns the channel dimension axis of the image. Args: image (`np.ndarray`): The image to get the channel dimension axis of. input_data_format (`ChannelDimension` or `str`, *optional*): The channel dimension format of the image. If `None`, will infer the channel dimension from the image. Returns: The channel dimension axis of the image. Nr]rUnsupported data format: )rvrr r`r!r8)r;rwr"r"r#get_channel_dimension_axisMs    ry channel_dimcCsZ|durt|}|tjkr|jd|jdfS|tjkr&|jd|jdfStd|)a Returns the (height, width) dimensions of the image. Args: image (`np.ndarray`): The image to get the dimensions of. channel_dim (`ChannelDimension`, *optional*): Which dimension the channel dimension is in. If `None`, will infer the channel dimension from the image. Returns: A tuple of the image's height and width. Nrx)rvrr rsr!r8)r;rzr"r"r#get_image_sizees   r~ image_size max_height max_widthc CsB|\}}||}||}t||}t||}t||} || fS)a Computes the output image size given the input image and the maximum allowed height and width. Keep aspect ratio. Important, even if image_height < max_height and image_width < max_width, the image will be resized to at least one of the edges be equal to max_height or max_width. For example: - input_size: (100, 200), max_height: 50, max_width: 50 -> output_size: (25, 50) - input_size: (100, 200), max_height: 200, max_width: 500 -> output_size: (200, 400) Args: image_size (`Tuple[int, int]`): The image to resize. max_height (`int`): The maximum allowed height. max_width (`int`): The maximum allowed width. )rZrr) rrrheightwidthZ height_scaleZ width_scaleZ min_scaleZ new_heightZ new_widthr"r"r##get_image_size_for_max_height_width}s   r annotationcCsVt|tr)d|vr)d|vr)t|dttfr)t|ddks't|ddtr)dSdS)Nimage_id annotationsrTFr+dictrNrTlenrr"r"r#"is_valid_annotation_coco_detections"rcCs^t|tr-d|vr-d|vr-d|vr-t|dttfr-t|ddks+t|ddtr-dSdS)NrZ segments_info file_namerTFrrr"r"r#!is_valid_annotation_coco_panoptics"rrcCtdd|DS)Ncsr?r*)rrAannr"r"r#rBrCz3valid_coco_detection_annotations..rDrr"r"r# valid_coco_detection_annotationsrcCr)Ncsr?r*)rrr"r"r#rBrCz2valid_coco_panoptic_annotations..rDrr"r"r#valid_coco_panoptic_annotationsrrtimeoutc Csttdgt|tre|ds|dr$tjtt j ||dj }nOt j |r1tj|}nB|dr=|dd}zt|}tjt|}Wn$tyd}z td|d |d }~wwt|tjjro|}ntd tj|}|d }|S) a3 Loads `image` to a PIL Image. Args: image (`str` or `PIL.Image.Image`): The image to convert to the PIL Image format. timeout (`float`, *optional*): The timeout value in seconds for the URL request. Returns: `PIL.Image.Image`: A PIL Image. Zvisionzhttp://zhttps://rz data:image/,rzIncorrect image source. Must be a valid URL starting with `http://` or `https://`, a valid path to an image file, or a base64 encoded string. Got z. Failed with NzuIncorrect format used for image. Should be an url linking to an image, a base64 string, a local path, or a PIL image.RGB)r load_imager+str startswithr,r-openrrequestsgetcontentospathisfilesplitbase64 decodebytesencode Exceptionr8 TypeErrorZImageOpsZexif_transposeconvert)r;rZb64er"r"r#rs2     rcsXt|ttfr&t|rt|dttfrfdd|DSfdd|DSt|dS)aLoads images, handling different levels of nesting. Args: images: A single image, a list of images, or a list of lists of images to load. timeout: Timeout for loading images. Returns: A single image, a list of images, a list of lists of images. rcsg|] }fdd|DqS)cg|]}t|dqSrrr@rr"r#rJz*load_images...r")rAZ image_grouprr"r#rJszload_images..crrrr@rr"r#rJrr)r+rNrTrr)r>rr"rr# load_imagess   r do_rescalerescale_factor do_normalize image_mean image_stddo_padsize_divisibilitydo_center_crop crop_size do_resizesizeresamplePILImageResamplingc Cs||r |dur td|r|durtd|r"|dus|dur"td|r,|dur,td| r:| dus6| dur width, then image will be rescaled to (size * height / width, size). resample (`int`, *optional*, defaults to `PILImageResampling.BILINEAR`): The filter to user for resampling. default_to_square (`bool`, *optional*, defaults to `True`): How to convert `size` when it is a single int. If set to `True`, the `size` will be converted to a square (`size`,`size`). If set to `False`, will replicate [`torchvision.transforms.Resize`](https://pytorch.org/vision/stable/transforms.html#torchvision.transforms.Resize) with support for resizing only the smallest edge and providing an optional `max_size`. max_size (`int`, *optional*, defaults to `None`): The maximum allowed for the longer edge of the resized image: if the longer edge of the image is greater than `max_size` after being resized according to `size`, then the image is resized again so that the longer edge is equal to `max_size`. As a result, `size` might be overruled, i.e the smaller edge may be shorter than `size`. Only used if `default_to_square` is `False`. Returns: image: A resized `PIL.Image.Image`. Nrrz max_size = zN must be strictly greater than the requested size for the smaller edge size = )r)rBILINEARrr+r,r-rrNrTrrrrr8resize) rr;rrZdefault_to_squaremax_sizerrZshortlongZrequested_new_shortZ new_shortZnew_longr"r"r#rs4   $ z"ImageFeatureExtractionMixin.resizecCs||t|ts||f}t|st|tjr8|jdkr"||}|jddvr0|jddn|jdd}n |j d|j df}|d|dd}||d}|d|dd}||d}t|t j j rr| ||||fS|jddvr{dnd}|st|tjr| ddd}t|r|ddd}|dkr||dkr|dkr||dkr|d||||fS|jdd t|d|dt|d|df} t|tjrtj|| d } n t|r|| } | d |dd} | |d} | d |dd} | |d}|| d| | | |f<|| 7}|| 7}|| 7}|| 7}| dtd|t| jd |td|t| jd |f} | S) a Crops `image` to the given size using a center crop. Note that if the image is too small to be cropped to the size given, it will be padded (so the returned result has the size asked). Args: image (`PIL.Image.Image` or `np.ndarray` or `torch.Tensor` of shape (n_channels, height, width) or (height, width, n_channels)): The image to resize. size (`int` or `Tuple[int, int]`): The size to which crop the image. Returns: new_image: A center cropped `PIL.Image.Image` or `np.ndarray` or `torch.Tensor` of shape: (n_channels, height, width). rprrorNTF.r{)rsr|)rr+rTrrOrPr`rrsrr,r-croprZpermuter[Z zeros_likeZ new_zerosrZ)rr;rZ image_shapetopbottomleftrightrZ new_shapeZ new_imageZtop_padZ bottom_padZleft_padZ right_padr"r"r# center_cropsP    ,   (2    4z'ImageFeatureExtractionMixin.center_cropcCs>||t|tjjr||}|dddddddfS)a Flips the channel order of `image` from RGB to BGR, or vice versa. Note that this will trigger a conversion of `image` to a NumPy array if it's a PIL Image. Args: image (`PIL.Image.Image` or `np.ndarray` or `torch.Tensor`): The image whose color channels to flip. If `np.ndarray` or `torch.Tensor`, the channel dimension should be first. Nr|)rr+r,r-rmrr"r"r#flip_channel_ordercs  z.ImageFeatureExtractionMixin.flip_channel_orderrcCsL|dur|ntjj}||t|tjjs||}|j||||||dS)a Returns a rotated copy of `image`. This method returns a copy of `image`, rotated the given number of degrees counter clockwise around its centre. Args: image (`PIL.Image.Image` or `np.ndarray` or `torch.Tensor`): The image to rotate. If `np.ndarray` or `torch.Tensor`, will be converted to `PIL.Image.Image` before rotating. Returns: image: A rotated `PIL.Image.Image`. N)rexpandcenter translate fillcolor)r,r-NEARESTrr+rrotate)rr;Zanglerrrrrr"r"r#rts   z"ImageFeatureExtractionMixin.rotater*)NT)F)NTN)NrNNN)rrr__doc__rrrrOrPrrrrrrmrrrrrrr"r"r"r#r.s "   4CKrannotation_formatsupported_annotation_formatscCsX||vrtdtd||tjurt|std|tjur(t|s*tddSdS)NzUnsupported annotation format: z must be one of zInvalid COCO detection annotations. Annotations must a dict (single image) or list of dicts (batch of images) with the following keys: `image_id` and `annotations`, with the latter being a list of annotations in the COCO format.zInvalid COCO panoptic annotations. Annotations must a dict (single image) or list of dicts (batch of images) with the following keys: `image_id`, `file_name` and `segments_info`, with the latter being a list of annotations in the COCO format.)r8formatr%r&rr'r)rrrr"r"r#validate_annotationss  rvalid_processor_keyscaptured_kwargscCs:t|t|}|rd|}td|ddSdS)Nz, zUnused or unrecognized kwargs: r_)set differencejoinrtru)rrZ unused_keysZunused_key_strr"r"r#validate_kwargss  rT)frozenc@szeZdZUdZdZeeed<dZeeed<dZ eeed<dZ eeed<dZ eeed<dZ eeed<d d Z dS) SizeDictz> Hashable dictionary to store image size information. Nrr longest_edge shortest_edgerrcCs$t||r t||Std|d)NzKey z not found in SizeDict.)hasattrgetattrKeyError)rkeyr"r"r# __getitem__s  zSizeDict.__getitem__)rrrrrrrr__annotations__rrrrrrr"r"r"r#rs  r)r]r*) NNNNNNNNNNNN)crrcollections.abcr dataclassesriortypingrrr3rOr packagingrutilsr r r r r rrrrrrZutils.constantsrrrrrrZ PIL.Imager,Z PIL.ImageOpsparse __version__ base_versionr-Z ResamplingrZtorchvision.transformsrrZ NEAREST_EXACTZBOXrZHAMMINGZBICUBICZLANCZOSZpil_torch_interpolation_mappingr2Z get_loggerrrtrPrNZ ImageInputrr%r(rrrrZAnnotationTyper0r1r<r=rGrSrUrVboolr\rarjrkrmrTrvryr~rrrrrrrrrrrrrr"r"r"r#s*    4         ' # $  ( "   ""&&$-     *a